INDEX

Explanations

technical terms and code-related language, particularly in the context of web development and data processing

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jak

-0.16

Ð¾Ð²Ð¸Ñĩ

-0.15

elsing

-0.15

terdam

-0.14

rah

-0.14

ulu

-0.13

 Wilkinson

-0.13

emez

-0.13

ornings

-0.13

Ã¶r

-0.13

POSITIVE LOGITS

ãĥĨãĥ«

0.15

oku

0.14

retty

0.14

 ÙĦØ°Ø§

0.14

ÛĮØ¯ÙĨ

0.13

itto

0.13

.ml

0.13

ÅĻez

0.13

clr

0.13

standing

0.13

Activations Density 0.148%

technical terms and code-related language, particularly in the context of web development and data processing

No Comments

No Known Activations